Ongoing research training transformer models at scale

303 份 AI/LLM 中文讲义，支持在线阅读、PDF 下载和 LaTeX 源码查看 | Stanford CS336/CS224R/CS25 | Berkeley LLM Agents | Agent 工程实践

One config to rule all your AI agents: portable (every project, every session), effective (curated writing, routing, skills), and safer (destructive-command guard).

(EACL'26 Main) Instructional Agents: Reducing Teaching Faculty Workload through Multi-Agent Instructional Design

Meta-Harness: 76.4% on Terminal-Bench 2.0 (Claude Opus 4.6)

Vero: An Open RL Recipe for General Visual Reasoning

Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepowe…

Agentic Risk Standard is a settlement-layer standard for trustworthy transactions with AI Agent

This is the official code base of AgentNetTool in OpenCUA. Website: https://opencua.xlang.ai/

The official repo of our paper, "SWE-Skills-Bench:Do Agent Skills Actually Help in Real-World Software Engineering?"

Official code for "SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization"

This is the official implementation of the CVPR 2026 paper: "Scaling Test-Time Robustness of Vision-Language Models via Self-Critical Inference Framework"

[ACL 2026 main] CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution

The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.

This is the official implementation of our paper "SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning"

"ClawTeam: Agent Swarm Intelligence" (One Command → Full Automation)

A Claude Code plugin that shows what's happening - context usage, active tools, running agents, and todo progress

Personal agent configuration for Codex and Claude Code. Not intended for general use.

A visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.

The code of Advancing Expert Specialization for Better MoE (NeurIPS2025 oral)

800,000 step-level correctness labels on LLM solutions to MATH problems